arXiv subjects

Muhammad Shafique

Publications and source records attributed to Muhammad Shafique.

At least 145 records · Page 8Linked to original sources

arXiv2025

NeuroNAS: Enhancing Efficiency of Neuromorphic In-Memory Computing for Intelligent Mobile Agents through Hardware-Aware Spiking Neural Architecture Search

Intelligent mobile agents (e.g., UGVs and UAVs) typically demand low power/energy consumption when solving their machine learning (ML)-based tasks, since they are usually powered by portable batteries with limited capacity. A potential solution is employing neuromorphic computing with Spiking Neural Networks (SNNs), which leverages event-based computation to enable ultra-low power/energy ML algorithms. To maximize the performance efficiency of SNN inference, the In-Memory Computing (IMC)-based hardware accelerators with emerging device technologies (e.g., RRAM) can be employed. However, SNN models are typically developed without considering constraints from the application and the underlying IMC hardware, thereby hindering SNNs from reaching their full potential in performance and efficiency. To address this, we propose NeuroNAS, a novel framework for developing energyefficient neuromorphic IMC for intelligent mobile agents using hardware-aware spiking neural architecture search (NAS), i.e., by quickly finding an SNN architecture that offers high accuracy under the given constraints (e.g., memory, area, latency, and energy consumption). Its key steps include: optimizing SNN operations to enable efficient NAS, employing quantization to minimize the memory footprint, developing an SNN architecture that facilitates an effective learning, and devising a systematic hardware-aware search algorithm to meet the constraints. Compared to the state-of-the-art techniques, NeuroNAS quickly finds SNN architectures (with 8bit weight precision) that maintain high accuracy by up to 6.6x search time speed-ups, while achieving up to 92% area savings, 1.2x latency improvements, 84% energy savings across different datasets (i.e., CIFAR-10, CIFAR-100, and TinyImageNet-200); while the state-of-the-art fail to meet all constraints at once.

cs.NE↗

arXiv2025

QSViT: A Methodology for Quantizing Spiking Vision Transformers

Vision Transformer (ViT)-based models have shown state-of-the-art performance (e.g., accuracy) in vision-based AI tasks. However, realizing their capability in resource-constrained embedded AI systems is challenging due to their inherent large memory footprints and complex computations, thereby incurring high power/energy consumption. Recently, Spiking Vision Transformer (SViT)-based models have emerged as alternate low-power ViT networks. However, their large memory footprints still hinder their applicability for resource-constrained embedded AI systems. Therefore, there is a need for a methodology to compress SViT models without degrading the accuracy significantly. To address this, we propose QSViT, a novel design methodology to compress the SViT models through a systematic quantization strategy across different network layers. To do this, our QSViT employs several key steps: (1) investigating the impact of different precision levels in different network layers, (2) identifying the appropriate base quantization settings for guiding bit precision reduction, (3) performing a guided quantization strategy based on the base settings to select the appropriate quantization setting, and (4) developing an efficient quantized network based on the selected quantization setting. The experimental results demonstrate that, our QSViT methodology achieves 22.75% memory saving and 21.33% power saving, while also maintaining high accuracy within 2.1% from that of the original non-quantized SViT model on the ImageNet dataset. These results highlight the potential of QSViT methodology to pave the way toward the efficient SViT deployments on resource-constrained embedded AI systems.

cs.NE↗

arXiv2025

Designing Robust Quantum Neural Networks via Optimized Circuit Metrics

In this study, we investigated the robustness of Quanvolutional Neural Networks (QuNNs) in comparison to their classical counterparts, Convolutional Neural Networks (CNNs), against two adversarial attacks: Fast Gradient Sign Method (FGSM) and Projected Gradient Descent (PGD), for the image classification task on both Modified National Institute of Standards and Technology (MNIST) and Fashion-MNIST (FMNIST) datasets. To enhance the robustness of QuNNs, we developed a novel methodology that utilizes three quantum circuit metrics: expressibility, entanglement capability, and controlled rotation gate selection. Our analysis shows that these metrics significantly influence data representation within the Hilbert space, thereby directly affecting QuNN robustness. We rigorously established that circuits with higher expressibility and lower entanglement capability generally exhibit enhanced robustness under adversarial conditions, particularly at low-spectrum perturbation strengths where most attacks occur. Furthermore, our findings challenge the prevailing assumption that expressibility alone dictates circuit robustness; instead, we demonstrate that the inclusion of controlled rotation gates around the Z-axis generally enhances the resilience of QuNNs. Our results demonstrate that QuNNs exhibit up to 60% greater robustness on the MNIST dataset and 40% on the Fashion-MNIST dataset compared to CNNs. Collectively, our work elucidates the relationship between quantum circuit metrics and robust data feature extraction, advancing the field by improving the adversarial robustness of QuNNs.

quant-ph↗

arXiv2025

Replay4NCL: An Efficient Memory Replay-based Methodology for Neuromorphic Continual Learning in Embedded AI Systems

Neuromorphic Continual Learning (NCL) paradigm leverages Spiking Neural Networks (SNNs) to enable continual learning (CL) capabilities for AI systems to adapt to dynamically changing environments. Currently, the state-of-the-art employ a memory replay-based method to maintain the old knowledge. However, this technique relies on long timesteps and compression-decompression steps, thereby incurring significant latency and energy overheads, which are not suitable for tightly-constrained embedded AI systems (e.g., mobile agents/robotics). To address this, we propose Replay4NCL, a novel efficient memory replay-based methodology for enabling NCL in embedded AI systems. Specifically, Replay4NCL compresses the latent data (old knowledge), then replays them during the NCL training phase with small timesteps, to minimize the processing latency and energy consumption. To compensate the information loss from reduced spikes, we adjust the neuron threshold potential and learning rate settings. Experimental results on the class-incremental scenario with the Spiking Heidelberg Digits (SHD) dataset show that Replay4NCL can preserve old knowledge with Top-1 accuracy of 90.43% compared to 86.22% from the state-of-the-art, while effectively learning new tasks, achieving 4.88x latency speed-up, 20% latent memory saving, and 36.43% energy saving. These results highlight the potential of our Replay4NCL methodology to further advances NCL capabilities for embedded AI systems.

cs.NE↗

arXiv2025

HQNN-FSP: A Hybrid Classical-Quantum Neural Network for Regression-Based Financial Stock Market Prediction

Financial time-series forecasting remains a challenging task due to complex temporal dependencies and market fluctuations. This study explores the potential of hybrid quantum-classical approaches to assist in financial trend prediction by leveraging quantum resources for improved feature representation and learning. A custom Quantum Neural Network (QNN) regressor is introduced, designed with a novel ansatz tailored for financial applications. Two hybrid optimization strategies are proposed: (1) a sequential approach where classical recurrent models (RNN/LSTM) extract temporal dependencies before quantum processing, and (2) a joint learning framework that optimizes classical and quantum parameters simultaneously. Systematic evaluation using TimeSeriesSplit, k-fold cross-validation, and predictive error analysis highlights the ability of these hybrid models to integrate quantum computing into financial forecasting workflows. The findings demonstrate how quantum-assisted learning can contribute to financial modeling, offering insights into the practical role of quantum resources in time-series analysis.

q-fin.ST↗

arXiv2025

Approximate Computing Survey, Part II: Application-Specific & Architectural Approximation Techniques and Applications

The challenging deployment of compute-intensive applications from domains such as Artificial Intelligence (AI) and Digital Signal Processing (DSP), forces the community of computing systems to explore new design approaches. Approximate Computing appears as an emerging solution, allowing to tune the quality of results in the design of a system in order to improve the energy efficiency and/or performance. This radical paradigm shift has attracted interest from both academia and industry, resulting in significant research on approximation techniques and methodologies at different design layers (from system down to integrated circuits). Motivated by the wide appeal of Approximate Computing over the last 10 years, we conduct a two-part survey to cover key aspects (e.g., terminology and applications) and review the state-of-the art approximation techniques from all layers of the traditional computing stack. Part II of the survey classifies and presents the technical details of application-specific and architectural approximation techniques, which both target the design of resource-efficient processors/accelerators and systems. Moreover, it reports a quantitative analysis of the techniques and a detailed analysis of the application spectrum of Approximate Computing, and finally, it discusses open challenges and future directions.

cs.AR↗

arXiv2025

Approximate Computing Survey, Part I: Terminology and Software & Hardware Approximation Techniques

The rapid growth of demanding applications in domains applying multimedia processing and machine learning has marked a new era for edge and cloud computing. These applications involve massive data and compute-intensive tasks, and thus, typical computing paradigms in embedded systems and data centers are stressed to meet the worldwide demand for high performance. Concurrently, over the last 15 years, the semiconductor industry has established power efficiency as a first-class design concern. As a result, the community of computing systems is forced to find alternative design approaches to facilitate high-performance and power-efficient computing. Among the examined solutions, Approximate Computing has attracted an ever-increasing interest, which has resulted in novel approximation techniques for all the layers of the traditional computing stack. More specifically, during the last decade, a plethora of approximation techniques in software (programs, frameworks, compilers, runtimes, languages), hardware (circuits, accelerators), and architectures (processors, memories) have been proposed in the literature. The current article is Part I of a comprehensive survey on Approximate Computing. It reviews its motivation, terminology and principles, as well it classifies the state-of-the-art software & hardware approximation techniques, presents their technical details, and reports a comparative quantitative analysis.

cs.AR↗

arXiv2025

RL-TIME: Reinforcement Learning-based Task Replication in Multicore Embedded Systems

Embedded systems power many modern applications and must often meet strict reliability, real-time, thermal, and power requirements. Task replication can improve reliability by duplicating a task's execution to handle transient and permanent faults, but blindly applying replication often leads to excessive overhead and higher temperatures. Existing design-time methods typically choose the number of replicas based on worst-case conditions, which can waste resources under normal operation. In this paper, we present RL-TIME, a reinforcement learning-based approach that dynamically decides the number of replicas according to actual system conditions. By considering both the reliability target and a core-level Thermal Safe Power (TSP) constraint at run-time, RL-TIME adapts the replication strategy to avoid unnecessary overhead and overheating. Experimental results show that, compared to state-of-the-art methods, RL-TIME reduces power consumption by 63%, increases schedulability by 53%, and respects TSP 72% more often.

cs.LG↗

arXiv2025

Breaking the Limits of Quantization-Aware Defenses: QADT-R for Robustness Against Patch-Based Adversarial Attacks in QNNs

Quantized Neural Networks (QNNs) have emerged as a promising solution for reducing model size and computational costs, making them well-suited for deployment in edge and resource-constrained environments. While quantization is known to disrupt gradient propagation and enhance robustness against pixel-level adversarial attacks, its effectiveness against patch-based adversarial attacks remains largely unexplored. In this work, we demonstrate that adversarial patches remain highly transferable across quantized models, achieving over 70\% attack success rates (ASR) even at extreme bit-width reductions (e.g., 2-bit). This challenges the common assumption that quantization inherently mitigates adversarial threats. To address this, we propose Quantization-Aware Defense Training with Randomization (QADT-R), a novel defense strategy that integrates Adaptive Quantization-Aware Patch Generation (A-QAPA), Dynamic Bit-Width Training (DBWT), and Gradient-Inconsistent Regularization (GIR) to enhance resilience against highly transferable patch-based attacks. A-QAPA generates adversarial patches within quantized models, ensuring robustness across different bit-widths. DBWT introduces bit-width cycling during training to prevent overfitting to a specific quantization setting, while GIR injects controlled gradient perturbations to disrupt adversarial optimization. Extensive evaluations on CIFAR-10 and ImageNet show that QADT-R reduces ASR by up to 25\% compared to prior defenses such as PBAT and DWQ. Our findings further reveal that PBAT-trained models, while effective against seen patch configurations, fail to generalize to unseen patches due to quantization shift. Additionally, our empirical analysis of gradient alignment, spatial sensitivity, and patch visibility provides insights into the mechanisms that contribute to the high transferability of patch-based attacks in QNNs.

cs.CV↗

arXiv2025

A Survey of Adversarial Defenses in Vision-based Systems: Categorization, Methods and Challenges

Adversarial attacks have emerged as a major challenge to the trustworthy deployment of machine learning models, particularly in computer vision applications. These attacks have a varied level of potency and can be implemented in both white box and black box approaches. Practical attacks include methods to manipulate the physical world and enforce adversarial behaviour by the corresponding target neural network models. Multiple different approaches to mitigate different kinds of such attacks are available in the literature, each with their own advantages and limitations. In this survey, we present a comprehensive systematization of knowledge on adversarial defenses, focusing on two key computer vision tasks: image classification and object detection. We review the state-of-the-art adversarial defense techniques and categorize them for easier comparison. In addition, we provide a schematic representation of these categories within the context of the overall machine learning pipeline, facilitating clearer understanding and benchmarking of defenses. Furthermore, we map these defenses to the types of adversarial attacks and datasets where they are most effective, offering practical insights for researchers and practitioners. This study is necessary for understanding the scope of how the available defenses are able to address the adversarial threats, and their shortcomings as well, which is necessary for driving the research in this area in the most appropriate direction, with the aim of building trustworthy AI systems for regular practical use-cases.

cs.CV↗

arXiv2025

QFAL: Quantum Federated Adversarial Learning

Quantum federated learning (QFL) merges the privacy advantages of federated systems with the computational potential of quantum neural networks (QNNs), yet its vulnerability to adversarial attacks remains poorly understood. This work pioneers the integration of adversarial training into QFL, proposing a robust framework, quantum federated adversarial learning (QFAL), where clients collaboratively defend against perturbations by combining local adversarial example generation with federated averaging (FedAvg). We systematically evaluate the interplay between three critical factors: client count (5, 10, 15), adversarial training coverage (0-100%), and adversarial attack perturbation strength (epsilon = 0.01-0.5), using the MNIST dataset. Our experimental results show that while fewer clients often yield higher clean-data accuracy, larger federations can more effectively balance accuracy and robustness when partially adversarially trained. Notably, even limited adversarial coverage (e.g., 20%-50%) can significantly improve resilience to moderate perturbations, though at the cost of reduced baseline performance. Conversely, full adversarial training (100%) may regain high clean accuracy but is vulnerable under stronger attacks. These findings underscore an inherent trade-off between robust and standard objectives, which is further complicated by quantum-specific factors. We conclude that a carefully chosen combination of client count and adversarial coverage is critical for mitigating adversarial vulnerabilities in QFL. Moreover, we highlight opportunities for future research, including adaptive adversarial training schedules, more diverse quantum encoding schemes, and personalized defense strategies to further enhance the robustness-accuracy trade-off in real-world quantum federated environments.

cs.LG↗

arXiv2025

Exploring the Robustness and Transferability of Patch-Based Adversarial Attacks in Quantized Neural Networks

Quantized neural networks (QNNs) are increasingly used for efficient deployment of deep learning models on resource-constrained platforms, such as mobile devices and edge computing systems. While quantization reduces model size and computational demands, its impact on adversarial robustness-especially against patch-based attacks-remains inadequately addressed. Patch-based attacks, characterized by localized, high-visibility perturbations, pose significant security risks due to their transferability and resilience. In this study, we systematically evaluate the vulnerability of QNNs to patch-based adversarial attacks across various quantization levels and architectures, focusing on factors that contribute to the robustness of these attacks. Through experiments analyzing feature representations, quantization strength, gradient alignment, and spatial sensitivity, we find that patch attacks consistently achieve high success rates across bitwidths and architectures, demonstrating significant transferability even in heavily quantized models. Contrary to the expectation that quantization might enhance adversarial defenses, our results show that QNNs remain highly susceptible to patch attacks due to the persistence of distinct, localized features within quantized representations. These findings underscore the need for quantization-aware defenses that address the specific challenges posed by patch-based attacks. Our work contributes to a deeper understanding of adversarial robustness in QNNs and aims to guide future research in developing secure, quantization-compatible defenses for real-world applications.

cs.CR↗

arXiv2025

NRQNN: The Role of Observable Selection in Noise-Resilient Quantum Neural Networks

This paper explores the complexities associated with training Quantum Neural Networks (QNNs) under noisy conditions, a critical consideration for Noisy Intermediate-Scale Quantum (NISQ) devices. We first demonstrate that Barren Plateaus (BPs), characterized by exponetially vanishing gradients, emerge more readily in noisy quantum environments than in ideal conditions. We then propose that careful selection of qubit measurement observable can make QNNs resilient against noise. To this end, we explore the effectiveness of various qubit measurement observables, including PauliX, PauliY, PauliZ, and a custom designed Hermitian observable, against three types of quantum noise: Phase Damping, Phase Flip, and Amplitude Damping. Our findings reveal that QNNs employing Pauli observables are prone to an earlier emergence of BPs, notably in noisy environments, even with a smaller qubit count of four qubits. Conversely, the custom designed Hermitian measurement observable exhibits significant resilience against all types of quantum noise, facilitating consistent trainability for QNNs up to 10 qubits. This study highlights the crucial role of observable selection and quantum noise consideration in enhancing QNN training, offering a strategic approach to improve QNN performance in NISQ era.

quant-ph↗

arXiv2025

Computational Advantage in Hybrid Quantum Neural Networks: Myth or Reality?

Hybrid Quantum Neural Networks (HQNNs) have gained attention for their potential to enhance computational performance by incorporating quantum layers into classical neural network (NN) architectures. However, a key question remains: Do quantum layers offer computational advantages over purely classical models? This paper explores how classical and hybrid models adapt their architectural complexity to increasing problem complexity. Using a multiclass classification problem, we benchmark classical models to identify optimal configurations for accuracy and efficiency, establishing a baseline for comparison. HQNNs, simulated on classical hardware (as common in the Noisy Intermediate-Scale Quantum (NISQ) era), are evaluated for their scaling of floating-point operations (FLOPs) and parameter growth. Our findings reveal that as problem complexity increases, HQNNs exhibit more efficient scaling of architectural complexity and computational resources. For example, from 10 to 110 features, HQNNs show an 53.1% increase in FLOPs compared to 88.1% for classical models, despite simulation overheads. Additionally, the parameter growth rate is slower in HQNNs (81.4%) than in classical models (88.5%). These results highlight HQNNs' scalability and resource efficiency, positioning them as a promising alternative for solving complex computational problems.

quant-ph↗

arXiv2025

NYU CTF Bench: A Scalable Open-Source Benchmark Dataset for Evaluating LLMs in Offensive Security

Large Language Models (LLMs) are being deployed across various domains today. However, their capacity to solve Capture the Flag (CTF) challenges in cybersecurity has not been thoroughly evaluated. To address this, we develop a novel method to assess LLMs in solving CTF challenges by creating a scalable, open-source benchmark database specifically designed for these applications. This database includes metadata for LLM testing and adaptive learning, compiling a diverse range of CTF challenges from popular competitions. Utilizing the advanced function calling capabilities of LLMs, we build a fully automated system with an enhanced workflow and support for external tool calls. Our benchmark dataset and automated framework allow us to evaluate the performance of five LLMs, encompassing both black-box and open-source models. This work lays the foundation for future research into improving the efficiency of LLMs in interactive cybersecurity tasks and automated task planning. By providing a specialized benchmark, our project offers an ideal platform for developing, testing, and refining LLM-based approaches to vulnerability detection and resolution. Evaluating LLMs on these challenges and comparing with human performance yields insights into their potential for AI-driven cybersecurity solutions to perform real-world threat management. We make our benchmark dataset open source to public https://github.com/NYU-LLM-CTF/NYU_CTF_Bench along with our playground automated framework https://github.com/NYU-LLM-CTF/llm_ctf_automation.

cs.CR↗

arXiv2025

Model Cascading for Code: A Cascaded Black-Box Multi-Model Framework for Cost-Efficient Code Completion with Self-Testing

The rapid advancement of large language models (LLMs) has significantly improved code completion tasks, yet the trade-off between accuracy and computational cost remains a critical challenge. While using larger models and incorporating inference-time self-testing algorithms can significantly improve output accuracy, they incur substantial computational expenses at the same time. Furthermore, servers in real-world scenarios usually have a dynamic preference on the cost-accuracy tradeoff, depending on the budget, bandwidth, the concurrent user volume, and users' sensitivity to wrong answers. In this work, we introduce a novel framework combining model cascading and inference-time self-feedback algorithms to find multiple near-optimal self-testing options on the cost-accuracy tradeoff in LLM-based code generation. Our approach leverages self-generated tests to both enhance accuracy and evaluate model cascading decisions. As a blackbox inference-time method, it requires no access to internal model parameters. We further propose a threshold-based algorithm to determine when to deploy larger models and a heuristic to optimize the number of solutions, test cases, and test lines generated per model, based on budget constraints. Experimental results show that our cascading approach reduces costs by an average of 26%, and up to 70% in the best case, across various model families and datasets, while maintaining or improving accuracy in natural language generation tasks compared to both random and optimal single-model self-testing schemes. To our knowledge, this is the first work to provide a series of choices for optimizing the cost-accuracy trade-off in LLM code generation with self-testing.

cs.SE↗

arXiv2025

MoENAS: Mixture-of-Expert based Neural Architecture Search for jointly Accurate, Fair, and Robust Edge Deep Neural Networks

There has been a surge in optimizing edge Deep Neural Networks (DNNs) for accuracy and efficiency using traditional optimization techniques such as pruning, and more recently, employing automatic design methodologies. However, the focus of these design techniques has often overlooked critical metrics such as fairness, robustness, and generalization. As a result, when evaluating SOTA edge DNNs' performance in image classification using the FACET dataset, we found that they exhibit significant accuracy disparities (14.09%) across 10 different skin tones, alongside issues of non-robustness and poor generalizability. In response to these observations, we introduce Mixture-of-Experts-based Neural Architecture Search (MoENAS), an automatic design technique that navigates through a space of mixture of experts to discover accurate, fair, robust, and general edge DNNs. MoENAS improves the accuracy by 4.02% compared to SOTA edge DNNs and reduces the skin tone accuracy disparities from 14.09% to 5.60%, while enhancing robustness by 3.80% and minimizing overfitting to 0.21%, all while keeping model size close to state-of-the-art models average size (+0.4M). With these improvements, MoENAS establishes a new benchmark for edge DNN design, paving the way for the development of more inclusive and robust edge DNNs.

cs.LG↗

arXiv2025

Quantum Neural Networks: A Comparative Analysis and Noise Robustness Evaluation

In current noisy intermediate-scale quantum (NISQ) devices, hybrid quantum neural networks (HQNNs) offer a promising solution, combining the strengths of classical machine learning with quantum computing capabilities. However, the performance of these networks can be significantly affected by the quantum noise inherent in NISQ devices. In this paper, we conduct an extensive comparative analysis of various HQNN algorithms, namely Quantum Convolution Neural Network (QCNN), Quanvolutional Neural Network (QuanNN), and Quantum Transfer Learning (QTL), for image classification tasks. We evaluate the performance of each algorithm across quantum circuits with different entangling structures, variations in layer count, and optimal placement in the architecture. Subsequently, we select the highest-performing architectures and assess their robustness against noise influence by introducing quantum gate noise through Phase Flip, Bit Flip, Phase Damping, Amplitude Damping, and the Depolarizing Channel. Our results reveal that the top-performing models exhibit varying resilience to different noise gates. However, in most scenarios, the QuanNN demonstrates greater robustness across various quantum noise channels, consistently outperforming other models. This highlights the importance of tailoring model selection to specific noise environments in NISQ devices.

quant-ph↗